© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20990
    Prev
    Next
    INDEX
    Explanations

    adapter

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires whenever it encounters the word “adapter.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     église
    -2.69
    ╽
    -2.67
    衚
    -2.63
     trovano
    -2.52
     quatrième
    -2.50
    想法
    -2.41
     troisième
    -2.34
    普通人
    -2.34
    ズニー
    -2.33
     derselben
    -2.33
    POSITIVE LOGITS
    the
    2.95
     gle
    2.72
    怎么可能
    2.56
    じゃあ
    2.55
    \
    2.50
    焄
    2.47
    勍
    2.42
    怎么会
    2.41
    𝓻
    2.36
    瘣
    2.36
    Activations Density 0.009%

    No Known Activations